Hacker News
Show HN: Omni – Open-source workplace search and chat, built on Postgres
Hacker News · Mar 2, 2026 · Collected from RSS
Summary
Hey HN! Over the past few months, I've been working on building Omni - a workplace search and chat platform that connects to apps like Google Drive/Gmail, Slack, Confluence, etc. Essentially an open-source alternative to Glean, fully self-hosted. I noticed that some orgs find Glean to be expensive and not very extensible. I wanted to build something that small to mid-size teams could run themselves, so I decided to build it all on Postgres (ParadeDB to be precise) and pgvector. No Elasticsearch, or dedicated vector databases. I figured Postgres is more than capable of handling the level of scale required. To bring up Omni on your own infra, all it takes is a single `docker compose up`, and some basic configuration to connect your apps and LLMs. What it does: - Syncs data from all connected apps and builds a BM25 index (ParadeDB) and HNSW vector index (pgvector) - Hybrid search combines results from both - Chat UI where the LLM has tools to search the index - not just basic RAG - Traditional search UI - Users bring their own LLM provider (OpenAI/Anthropic/Gemini) - Connectors for Google Workspace, Slack, Confluence, Jira, HubSpot, and more - Connector SDK to build your own custom connectors Omni is in beta right now, and I'd love your feedback, especially on the following: - Has anyone tried self-hosting workplace search and/or AI tools, and what was your experience like? - Any concerns with the Postgres-only approach at larger scales? Happy to answer any questions! The code: https://github.com/getomnico/omni (Apache 2.0 licensed) Comments URL: https://news.ycombinator.com/item?id=47215427 Points: 17 # Comments: 3
Full Article
Omni is an AI Assistant and Search platform for the Workplace. Connects to your workplace apps, helps employees find information and get work done. Features • Architecture • Docs • Deploy • Contributing Features Unified Search: Connect Google Drive/Gmail, Slack, Confluence, Jira, and more. Full-text (BM25) and semantic (pgvector) search across all of them. AI Agent: Chat interface with tool use: searches your connected apps, reads documents, and executes Python/bash in a sandboxed container to analyze data. Self-hosted: Runs entirely on your infrastructure. No data leaves your network. Permission Inheritance: Respects source system permissions. Users only see data they're already authorized to access. Bring Your Own LLM: Anthropic, OpenAI, Gemini, or open-weight models via vLLM. Simple Deployment: Docker Compose for single-server setups, Terraform for production AWS/GCP deployments. Architecture Omni uses Postgres (ParadeDB) for everything: BM25 full-text search, pgvector semantic search, and all application data. No Elasticsearch, no dedicated vector database. One database to tune, backup, and monitor. Core services are written in Rust (searcher, indexer, connector-manager), Python (AI/LLM orchestration), and SvelteKit (web frontend). Each data source connector runs as its own lightweight container, allowing connectors to use different languages and dependencies without affecting each other. The AI agent can execute code in a sandboxed container that runs on an isolated Docker network (no access to internal services or the internet), with Landlock filesystem restrictions, resource limits, and a read-only root filesystem. See the full architecture documentation for more details. Deployment Omni can be deployed entirely on your own infra. See our deployment guides: Docker Compose Terraform (AWS/GCP) Supported Integrations Google Workspace: Drive, Gmail Slack: Messages, files, public channels Confluence: Pages, attachments, spaces Jira: Issues and projects Web: Public websites, documentation and help pages Fireflies: Meeting transcripts HubSpot: Contacts, companies, deals, tickets Local Files: File system indexing Contributing See CONTRIBUTING.md for development setup and guidelines. License Apache License 2.0. See LICENSE for details.
Share this story